# JSON Whisperer: Efficient JSON Editing with LLMs

arXiv: https://arxiv.org/abs/2510.04717 · HTML: https://mlsanity.com/paper/2510.04717/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Exploring the Capabilities of LLMs for Code Change Related Tasks](https://mlsanity.com/paper/2407.02824/) (2024)
- [Parsing Gigabytes of JSON per Second](https://mlsanity.com/paper/1902.08318/) (2019)
- [GUIDE: LLM-Driven GUI Generation Decomposition for Automated Prototyping](https://mlsanity.com/paper/2502.21068/) (2025)

## Built on by (most cited first, 2 of 2)

- [LLM-assisted gNB Parameter Configuration for Radio Access Network](https://mlsanity.com/paper/2606.20574/) (2026)
- [SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR](https://mlsanity.com/paper/2607.05484/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can modify JSON documents through natural language commands, but current approaches regenerate entire structures for each edit, resulting in computational inefficiency. We present JSON Whisperer, a framework that enables LLMs to generate RFC 6902 diff patches-expressing only the necessary modifications-rather than complete documents. We identify two key challenges in patch-based editing: (1) LLMs often miss related updates when generating isolated patches, and (2) array manipulations require tracking index shifts across operations, which LLMs handle poorly. To address these issues, we introduce EASE (Explicitly Addressed Sequence Encoding), which transforms arrays into dictionaries with stable keys, eliminating index arithmetic complexities. Our evaluation shows that patch generation with EASE reduces token usage by 31% while maintaining edit quality within 5% of full regeneration with particular gains for complex instructions and list manipulations. The dataset is available at: https://github.com/emnlp2025/JSON-Whisperer/